Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 19, 2024

A Unsupervised graph comparison learning-based click-through rate prediction model

View Full Paper
Ask AI
Bookmark
Share

Authors

MHMing-Xiang HeXBXina BoGLGuan Li

Discussion

Loading...

Member takes

Overview

Comparative benchmark demonstrates superior click-through rate prediction across three open-source datasets, highlighting that graph denoising improves recommendation precision.

Key Points

  • Unsupervised graph comparison learning enhances click-through rate prediction accuracy by pruning noisy feature interactions from graph structures.
  • Evaluations on three open-source datasets show superior click-through rate prediction accuracy, consistently outperforming eight baseline models.
  • Metric learning establishes an anchor graph optimized via contrast loss, which may enable robust recommendation systems by removing spurious edges.

Cite This Study

He et al. (2024) studied this question.

synapsesocial.com/papers/68e5fc74b6db64358759055fhttps://doi.org/10.21203/rs.3.rs-4604800/v1
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Periodic Graph Neural Networks for Click-Through Rate Prediction in Online Advertising2025 · 3 citations
  2. 2Click-through rate prediction model based on graph networks and feature squeeze-and-excitation mechanism2024 · 3 citations
  3. 3AdaGIN: Adaptive Graph Interaction Network for Click-Through Rate Prediction2024 · 5 citations
  4. 4CETN: Contrast-enhanced Through Network for Click-Through Rate Prediction2024 · 7 citations
  5. 5Ad Click-Through Rate Prediction: A Comparative Study of Machine Learning Models2024 · 10 citations